[PR #7615] Allow Compile on older GPUs - still on CUDA 11.3 #43717

Open
opened 2026-04-24 23:18:41 -05:00 by GiteaMirror · 0 comments
Owner

📋 Pull Request Information

Original PR: https://github.com/ollama/ollama/pull/7615
Author: @langstonmeister
Created: 11/11/2024
Status: 🔄 Open

Base: mainHead: custom


📝 Commits (2)

📊 Changes

2 files changed (+2 additions, -2 deletions)

View changed files

📝 discover/gpu.go (+1 -1)
📝 llama/make/Makefile.cuda_v11 (+1 -1)

📄 Description

My Tesla k40s are still able to run this version of CUDA, but are technically on Compute 3.5. These commits will allow them to compile and run the software, and are working well for me.


🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.

## 📋 Pull Request Information **Original PR:** https://github.com/ollama/ollama/pull/7615 **Author:** [@langstonmeister](https://github.com/langstonmeister) **Created:** 11/11/2024 **Status:** 🔄 Open **Base:** `main` ← **Head:** `custom` --- ### 📝 Commits (2) - [`c863c6a`](https://github.com/ollama/ollama/commit/c863c6a318ce433275083042fc56e7313ddef4a3) update for older gpu - [`e79f528`](https://github.com/ollama/ollama/commit/e79f5287a18cb44627b971451b73b5bb8b96bdda) Update gpu.go ### 📊 Changes **2 files changed** (+2 additions, -2 deletions) <details> <summary>View changed files</summary> 📝 `discover/gpu.go` (+1 -1) 📝 `llama/make/Makefile.cuda_v11` (+1 -1) </details> ### 📄 Description My Tesla k40s are still able to run this version of CUDA, but are technically on Compute 3.5. These commits will allow them to compile and run the software, and are working well for me. --- <sub>🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.</sub>
GiteaMirror added the pull-request label 2026-04-24 23:18:41 -05:00
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#43717